Human-interactive robot for gait evaluation and navigation

Abstract

The paper describes human-interactive robot that supports gait training base on autonomous evaluation and navigation of human body movements. Robotic intervention in gait training is a promising method for prospective rehabilitation. In literature, gait training platforms such as power assisting limbs and body supporting mobile platforms have been studied well. These types of platforms, however, mainly assist physical movements of human limbs and physical body balance, and the advantage of cognitive assistance in rehabilitation is not fully discussed. In this framework, we focused on the importance of own motor recognition for recovery of motor functions. We implemented a robotic system to enhance the motor recognition in human-robot interaction. Lucia, the human-interactive medical robot, evaluates gait patterns from patients and navigates their gait training with audio, visual and somatosensory stimulation. In this paper, we will introduce novel algorithms of gait evaluation and navigation. We will then detail implementations of the algorithms for the robot and related systems. In experiments, we evaluated accuracy of leg tracking and landing detection. The experimental results show the effectiveness of the robotic evaluation and navigation for gait training.